# USECASE: Function can perform a task more easily and readably

# TEMPLATE: output <- function_name(input)

9 ^ (1 / 2)

x <- sqrt(9)
x

# ==============================================================================

# LESSON: We can also use functions to transform objects

y <- 9

sqrt(y)

# ==============================================================================

# LESSON: We can even use functions to transform the result of calculations

2 / 3

round(2 / 3)

# ==============================================================================

# LESSON: We can customize what a function does using arguments

# TEMPLATE: output <- function_name(argument, argument_name = argument_value)

round(2 / 3, digits = 2)

round(2 / 3, digits = 3)

# ==============================================================================

# LESSON: Some arguments are optional because they have default values

round(2 / 3) # the default value for digits is 0

round(2 / 3, digits = 0)

# LESSON: We can combine multiple elements into a vector

# TEMPLATE: vector_name <- c(element1, element2, element3)

x <- 4 9 16 25 # error

x <- c(4, 9, 16, 25)
x

y <- c(2, 3)
y

# ==============================================================================

# LESSON: We can also combine multiple vectors and elements

c(x, y)

c(x, y, 20)

# ==============================================================================

# USECASE: Math operators will transform each element individually

x + 1

x * 3

x # but again, this won't be saved unless you use assignment

# ==============================================================================

# USECASE: Some functions will also transform each element individually

sqrt(x)

log(x)

# ==============================================================================

# USECASE: Other functions will summarize the vector with a single number

length(x)

sum(x)

mean(x)

# USECASE: Strings are the main way to store character data in R
 
my_color <- red # error

my_color <- "red" # correct

# ==============================================================================

# USECASE: Strings can also store symbols not allowed in object names

dye <- "red#40"
dye

dyes <- c("red#40", "blue#02")
dyes

# ==============================================================================

# PITFALL: Many operations you can do to numbers won't work for strings

dyes + 1 # error

mean(dyes) # error

# ==============================================================================

# USECASE: But other operations work for both or even just for strings

length(dyes)

nchar(dyes)

dyes2 <- toupper(dyes)
dyes2

# USECASE: The stringr package adds a function to fix capitalization

students <- c("mary anne", "BENjamin", "Lee")

# ==============================================================================

# PITFALL: But we can't use that function without installing the package

str_to_title(students) # error

# ==============================================================================

# LESSON: Installing a package using RStudio

# - RStudio > Extras pane > Packages tab > Install button

# ==============================================================================

# PITFALL: We also need to load the package before we can use it

str_to_title(students) # error

# ==============================================================================

# LESSON: We load the package using library()

library("stringr")
str_to_title(students) #finally works!

# ==============================================================================

# LESSON: We can also keep our packages updated using RStudio

# RStudio > Extras pane > Packages tab > Update button

# SETUP: Install and load the tidyverse package

# Extras pane > Packages tab > Install

library(tidyverse)

# ==============================================================================

# LESSON: Create a tibble from vectors

x <- c(10, 20, 30, 40)
x

y <- x * 2 - 4
y

my_tibble <- tibble(x, y)
my_tibble

# ==============================================================================

# USECASE: You can mix different types of vectors in a single tibble

first_names <- c("Adam", "Billy", "Caitlyn", "Debra")

age_years <- c(12, 13, 10, NA)

guests <- tibble(first_names, age_years)
guests

# ==============================================================================

# TIP: To save time, you can also create the vectors in the tibble call

gradebook <- tibble(
  grade = c(95, 83, 90, 76),
  letter = c("a", "b", "a-", "c")
)
gradebook

# ==============================================================================

# PITFALL: Don't try to combine tibbles with different lengths

y <- c(1, 2, 3)
x <- c("a", "b")

tibble(y, x) #error

# ==============================================================================

# LESSON: However, the exception is R will "recycle" a single value

tibble(y, x = "a")

# ==============================================================================

# LESSON: You can "extract" a vector from a tibble using $

mytibble <- tibble(x = c(1, 2, 3, 4, 5), y = "test")

mytibble$x

mytibble$y

# ==============================================================================

# PITFALL: Don't try to extract a vector that doesn't exist

mytibble$z #error

# SETUP: Load the tidyverse package (if you haven't yet)

library(tidyverse)

# ==============================================================================

# USECASE: Create a tibble and write it to a file

gradebook <- tibble(
  id = c(123, 456, 789),
  grade = c("A", "B", "A")
)
gradebook

write_csv(gradebook, file = "gradebook.csv")

# NOTE: You can see the new file in Extras pane > Files tab.
# You can open the file in another program (e.g., Microsoft Excel).
# You can also email this file to someone else to share it.

# ==============================================================================

# PITFALL: Don't swap the order of the tibble and the file

write_csv("gradebook.csv", gradebook) # error

# ==============================================================================

# USECASE: Read in a file containing data

old_gradebook <- read_csv("gradebook.csv")
old_gradebook

# NOTE: read_csv() will examine and guess the data type of each variable.
# You can tell it the data type of each variable, but that is more advanced.

# ==============================================================================

# PITFALL: Don't use the read.csv() and write.csv() functions

old_gradebook <- read.csv("gradebook.csv") # not a tibble
old_gradebook

# SETUP: Load package and inspect example tibble

library(tidyverse) # includes the dplyr package
starwars

# ==============================================================================

# USECASE: Retain only the specified variables

sw <- select(starwars, name)
sw
sw <- select(starwars, name, sex, species)
sw

# ==============================================================================

# PITFALL: Don't forget to save the change with assignment

select(starwars, name, sex, species)
starwars # still includes all variables

# ==============================================================================

# USECASE: Retain all variables between two variables

sw <- select(starwars, name, hair_color:eye_color)
sw

# ==============================================================================

# USECASE: Retain all variables except the specified ones

sw <- select(starwars, -sex, -species)
sw
sw <- select(starwars, -c(sex, species))
sw
sw <- select(starwars, -c(hair_color:starships))
sw

# SETUP: Create example tibble

patients <- tibble(
  id = c("S1", "S2", "S3"),
  feet = c(6, 5, 5),
  inches = c(1, 7, 2),
  pounds = c(176.3, 124.9, 162.6)
)
patients

# ==============================================================================

# USECASE: Add one or more variables

p2 <- mutate(patients, sex = c("M", "F", "F"))
p2

ages <- c(32, 41, 29)
p2 <- mutate(patients, ages = ages)
p2

p2 <- mutate(
  patients, 
  sex = c("M", "F", "F"), 
  ages = ages
)
p2

# ==============================================================================

# USECASE: Compute variables

p2 <- mutate(patients, height = feet + inches / 12)
p2

p2 <- mutate(patients, ln_pounds = log(pounds))
p2

# ==============================================================================

# USECASE: Overwrite variables

patients <- mutate(patients, height = height / 3.281)
patients

# ==============================================================================

# USECASE: Duplicate variables

p2 <- mutate(patients, weight = pounds)
p2 # both weight and pounds exist

# USECASE: Change the name of one or more variables

starwars

sw <- rename(starwars, Character = name)
sw

sw <- rename(starwars, height_cm = height, mass_kg = mass)
sw

# ==============================================================================

# PITFALL: Don't swap the order and try old_name = new_name

sw <- rename(starwars, name = Character) # error

# ==============================================================================

# USECASE: Move variables before or after another variable

starwars

sw <- relocate(starwars, species, sex, .before = height)
sw

sw <- relocate(starwars, species, sex, .after = name)
sw

# ==============================================================================

# PITFALL: Don't forget the period!

sw <- relocate(starwars, sex, before = height) 
sw # height was accidentally renamed to before

# USECASE: Sort observations by a variable

starwars

sw <- arrange(starwars, height)
sw # sorted by height, ascending

sw <- arrange(starwars, name)
sw # sorted by name, alphabetically

# ==============================================================================

# USECASE: Sort observations by a variable, in reverse order

sw <- arrange(starwars, desc(height))
sw # sorted by height, descending

sw <- arrange(starwars, desc(name))
sw # sorted by name, reverse-alphabetically

# ==============================================================================

# USECASE: Sort observations by multiple variables

sw <- arrange(starwars, hair_color, mass)
sw # sorted by hair_color, then ties broken by mass

# USECASE: Retain only observations that meet a criterion

sw <- filter(starwars, mass > 100)
sw # only observations with mass greater than 100

sw <- filter(starwars, mass <= 100)
sw # only observations with mass less than or equal to 100

sw <- filter(starwars, species == "Human")
sw # only observations with species equal to Human

sw <- filter(starwars, species != "Human")
sw # only observations with species not equal to Human

# ==============================================================================

# PITFALL: Don't try to use a single = for testing equality

sw <- filter(starwars, height = 150) # error

sw <- filter(starwars, height == 150) # correct
sw 

# ==============================================================================

# PITFALL: Don't forget that R is case-sensitive

sw <- filter(starwars, species == "human")
sw # no observations left (because it should be Human)

# ==============================================================================

# USECASE: Retain only observations that meet complex criteria

sw <- filter(starwars, mass > 100 & height > 200)
sw # only observations with mass over 100 AND height over 200

sw <- filter(starwars, height < 100 | hair_color == "none")
sw # only observations with height under 100 OR hair_color equal to none

# ==============================================================================

# PITFALL: Don't forget to complete both conditions

sw <- filter(starwars, mass > 100 & < 200) # error

sw <- filter(starwars, mass > 100 & mass < 200) # correct
sw

# ==============================================================================

# PITFALL: Don't try to equate a string to a vector

sw <- filter(starwars, species == c("Human", "Droid")) # error

sw <- filter(starwars, species %in% c("Human", "Droid")) # correct
sw

# SETUP: Enable the pipe operator shortcut

# Tools > Global Options... > Code tab > Check "Use Native Pipe Operator"

# Type out |> or press Ctrl+Shift+M (Windows) / Cmd+Shift+M (Mac)

# ==============================================================================

# LESSON: The pipe pushes objects to a function as its first argument

# TEMPLATE: x |> function_name() is the same as function_name(x)

x <- 10

y <- sqrt(x)
y

y <- x |> sqrt()
y

# ==============================================================================

# PITFALL: Don't forget to remove the object from the function call

x |> sqrt(x) # wrong

x |> sqrt() # correct

# ==============================================================================

# USECASE: You can still use arguments when piping

z <- round(3.14, digits = 1)
z

z <- 3.14 |> round(digits = 1)
z

# ==============================================================================

# USECASE: Pipes are useful with tibbles and wrangling verbs

starwars

sw <- select(starwars, name, species, height)
sw

sw <- starwars |> select(name, species, height)
sw

# ==============================================================================

# PITFALL: Don't add a pipe without a step after it

sw <- starwars |> select(name, species, height) |> # error

# USECASE: You can chain multiple pipes together to make a pipeline

x <- 10 |> sqrt() |> round()
x

# ==============================================================================

# TIP: If you want to see the output of a pipeline, you can pipe to print()

x <- 10 |> sqrt() |> round() |> print()

# ==============================================================================

# TIP: To make your pipelines more readable, move each step to a new line

x <- 
  10 |> 
  sqrt() |> 
  round() |>
  print()

# ==============================================================================

# PITFALL: Don't put the pipe at the beginning of a line, though

x <- 
  10 
  |> sqrt()
  |> round()
  |> print() # error

# ==============================================================================

# USECASE: Chain together a series of verbs to flexibly wrangle data

tallones <- 
  starwars |> 
  select(name, species, height) |> 
  rename(height_cm = height) |> 
  mutate(height_ft = height_cm / 30.48) |>  
  filter(height_ft > 7) |> 
  arrange(desc(height_ft)) |>  
  print()

# USECASE: Ask 10 kids to order 1: nuggets, 2: pizza, or 3: salad

food <- c(2, 2, 1, 2, 1, 2, 1, 1, 2, 2)
food

# ==============================================================================

# LESSON: We can turn this vector into a factor with factor()

food2 <- factor(food, levels = c(1, 2, 3))
food2

food3 <- factor(food, levels = c(1, 2, 3),
                labels = c("nuggets", "pizza", "salad"))
food3

# ==============================================================================

# USECASE: We can also quickly and easily count each level with table()

table(food3)

# ==============================================================================

# PITFALL: Don't confuse levels and labels

food4 <- factor(food, labels = c(1, 2, 3),
                levels = c("nuggets", "pizza", "salad"))
food4 # full of <NA> because it can't find these levels

# ==============================================================================

# USECASE: You can also just enter strings directly (as self-labels)

genre <- c("pop", "metal", "pop", "rock", "rap", "rap", "pop", "rock")
genre

genre2 <- factor(genre) # observed levels will be assigned alphabetically
genre2

table(genre2)

# ==============================================================================

# LESSON: If ordinal, enter levels low-to-high and add ordered = TRUE

salsa <- c("hot", "mild", "medium", "mild", "medium", "medium")

salsa2 <- factor(salsa, 
                 levels = c("mild", "medium", "hot"), 
                 ordered = TRUE)
salsa2 

# NOTE: We may want to visualize or model ordinal factors differently

# ==============================================================================

# USECASE: Working with factors in a tibble

cereal <- read_csv("cereal.csv")
cereal

cereal2 <- mutate(cereal, mfr = factor(mfr), type = factor(type))
cereal2

table(cereal2$mfr)

table(cereal2$type)

# SETUP: We will need tidyverse for the read and mutate functions

library(tidyverse)

# ==============================================================================

# PITFALL: Number codes for missingness will mess up calculations in R

heights <- c(149, 158, -999) # here we use -999 to represent a missing value

range(heights)

mean(heights)

log(heights) # our missing value is no longer -999

# ==============================================================================

# USECASE: Use NA for missingness instead

heights2 <- c(149, 158, NA)
heights2

log(heights2) # the NA stayed an NA (due to contagiousness)

# ==============================================================================

# LESSON: Use na.rm = TRUE to do a summary function ignoring the NAs

mean(heights2) # the mean is an NA (due to contagiousness)

mean(heights2, na.rm = TRUE)

range(heights2, na.rm = TRUE)

# ==============================================================================

# USECASE: Dealing with missing values in tibbles

cereal <- read_csv("cereal.csv")

cereal$rating

range(cereal$rating)

# ==============================================================================

# LESSON: Use na_if() to convert specific values to NA while mutating

cereal2 <- mutate(cereal, rating = na_if(rating, -999))

cereal2$rating

range(cereal2$rating, na.rm = TRUE)

# ==============================================================================

# LESSON: Use read_csv(na) to convert specific values to NA while reading

cereal3 <- read_csv("cereal.csv", na = "-999")

cereal3$rating

range(cereal3$rating, na.rm = TRUE)

# SETUP: We will need tidyverse and an example dataset

library(tidyverse)

sales <- 
  tibble(
    customer = c(1, 2, 3, 1, 3),
    store = c("A", "A", "A", "B", "B"),
    items = c(25, 20, 16, 10, 5),
    spent = c(685, 590, 392, 185, 123)
  ) |> 
  print()

# ==============================================================================

# USECASE: Summarize the typical sales

my_summary <- 
  sales |> 
  summarize(
    avg_items = mean(items),
    avg_spent = mean(spent)
  ) |> 
  print()

# ==============================================================================

# PITFALL: Don't use summary() instead of summarize()

my_summary <- 
  sales |> 
  summary(
    avg_items = mean(items),
    avg_spent = mean(spent)
  ) |> 
  print() # not a tibble

# ==============================================================================

# USECASE: Use more than one summary function

my_summary <- 
  sales |> 
  summarize(
    total_items = sum(items),
    total_spent = sum(spent),
    avg_items = mean(items),
    avg_spent = mean(spent)
  ) |> 
  print()

# ==============================================================================

# USECASE: Use counting functions

my_counts <- 
  sales |> 
  summarize(
    n_sales = n(),
    n_customers = n_distinct(customer),
    n_stores = n_distinct(store)
  ) |> 
  print()

# SETUP: We will need tidyverse and an example dataset

library(tidyverse)

sales <- 
  tibble(
    customer = c(1, 2, 3, 1, 3),
    store = c("A", "A", "A", "B", "B"),
    items = c(25, 20, 16, 10, 5),
    spent = c(685, 590, 392, 185, 123)
  ) |> 
  print()

# ==============================================================================

# LESSON: We pass a tibble through group_by to group it

sales

sales |> group_by(store) # note the display says "grouped"

# ==============================================================================

# USECASE: We can then summarize and get stats per group

sales |> 
  group_by(store) |> 
  summarize(
    customers = n_distinct(customer),
    items_sold = sum(items),
    total_sales = sum(spent),
    avg_items = mean(items),
    avg_spent = mean(spent)
  )

# ==============================================================================

# SETUP: Let's get a larger, more realistic dataset

# Extra pane > Packages tab > Install > nycflights13

library("nycflights13")

flights

# ==============================================================================

# USECASE: Find the carrier with the lowest average delays

flights |> 
  group_by(carrier) |> 
  summarize(m_delay = mean(dep_delay, na.rm = TRUE)) |> 
  arrange(m_delay)

# ==============================================================================

# LESSON: We can also group by multiple variables

# USECASE: Let's find the day of the year with the most flights

flights |> 
  group_by(month, day) |> 
  summarize(n_flights = n()) |> 
  arrange(desc(n_flights))

# SETUP: We will need tidyverse and an example dataset

library(tidyverse)

mpg

# ==============================================================================

# LESSON: First, set the data to a tibble
p <- ggplot(data = mpg)
p

# ==============================================================================

# LESSON: Next, set the aesthetic mappings with aes()

p <- ggplot(data = mpg, mapping = aes(x = displ, y = hwy))
p

# ==============================================================================

# TIP: You can leave off the optional argument names

p <- ggplot(mpg, aes(x = displ, y = hwy))
p

# ==============================================================================

# LESSON: Next, set the positional scales

p <- ggplot(mpg, aes(x = displ, y = hwy)) +
  scale_x_continuous(
    name = "Engine Size (in liters)", 
    limits = c(1, 7), 
    breaks = 1:7
  ) +
  scale_y_continuous(
    name = "Highway Fuel Efficiency (in miles/gallon)",
    limits = c(10, 50),
    breaks = c(10, 20, 30, 40, 50)
  )
p

# ==============================================================================

# LESSON: Finally, add a point geom

p <- 
  ggplot(mpg, aes(x = displ, y = hwy)) + 
  scale_x_continuous(
    name = "Engine Size (in liters)", 
    limits = c(1, 7), 
    breaks = 1:7
  ) +
  scale_y_continuous(
    name = "Highway Fuel Efficiency (in miles/gallon)",
    limits = c(10, 50),
    breaks = c(10, 20, 30, 40, 50)
  ) +
  geom_point()

# ==============================================================================

# TIP: If you leave off the scales, R will try to guess

p <- ggplot(mpg, aes(x = displ, y = hwy)) + geom_point()
p

# ==============================================================================

# LESSON: We can also customize the geom with arguments

p <- ggplot(mpg, aes(x = displ, y = hwy)) + 
  geom_point(color = "red", shape = "square", size = 2)
p

# SETUP: We will need tidyverse and an example dataset

library(tidyverse)

mpg

# ==============================================================================

# USECASE: Add a smooth geom (i.e., line of best fit)

ggplot(mpg, aes(x = displ, y = hwy)) +
  geom_point() +
  geom_smooth()

ggplot(mpg, aes(x = displ, y = hwy)) +
  geom_point() +
  geom_smooth(method = "lm")

# ==============================================================================

# USECASE: Add a line geom (i.e., connecting points)

economics

ggplot(economics, aes(x = date, y = unemploy)) + 
  geom_point()

ggplot(economics, aes(x = date, y = unemploy)) + 
  geom_point() +
  geom_line(color = "orange", size = 1)

ggplot(economics, aes(x = date, y = unemploy)) + 
  geom_line(color = "orange", size = 1) +
  geom_point()

# ==============================================================================

# USECASE: Add reference line geoms

ggplot(economics, aes(x = date, y = unemploy)) + 
  geom_hline(yintercept = 0, color = "orange", size = 1) +
  geom_line(color = "blue", size = 1) +
  geom_point()

ggplot(economics, aes(x = date, y = unemploy)) + 
  geom_vline(xintercept = 7.5, color = "orange", size = 1) +
  geom_line(color = "blue", size = 1) +
  geom_point() 

ggplot(economics, aes(x = date, y = unemploy)) + 
  geom_abline(intercept = 4000, slope = 0.5, color = "orange", size = 1) +
  geom_line(color = "blue", size = 1) +
  geom_point() 

# SETUP: We will need tidyverse and an example dataset

library(tidyverse)

mpg

# ==============================================================================

# USECASE: Continuous color scales work well with numeric variables

ggplot(mpg, aes(x = hwy, y = cty, color = displ)) +
  geom_point(size = 4)

ggplot(mpg, aes(x = hwy, y = cty, color = displ)) +
  geom_point(size = 4) +
  scale_color_continuous(type = "viridis")

# ==============================================================================

# USECASE: Use a discrete color scale with categorical variables

ggplot(mpg, aes(x = displ, y = hwy, color = drv)) +
  geom_point()

ggplot(mpg, aes(x = displ, y = hwy, color = drv)) +
  geom_point() +
  scale_color_discrete(
    name = "Drivetrain", 
    breaks = c("4", "f", "r"), 
    labels = c("Four Wheel", "Front Wheel", "Rear Wheel")
  )

# ==============================================================================

# PITFALL: Don't forget to set categorical variables as factors

ggplot(mpg, aes(x = displ, y = hwy, color = cyl)) + 
  geom_point() # R guesses you want a continuous scale

ggplot(mpg, aes(x = displ, y = hwy, color = factor(cyl))) + 
  geom_point() + 
  scale_color_discrete(name = "Cylinders")

# ==============================================================================

# LESSON: Set a geom's color aesthetic to make it always that color

ggplot(mpg, aes(x = displ, y = hwy)) +
  geom_point(color = "red")

# ==============================================================================

# PITFALL: However, do this inside of geom() not aes()

ggplot(mpg, aes(x = displ, y = hwy, color = "blue")) + 
  geom_point() #unintended

# ==============================================================================

# LESSON: If you both set and map color, the setting will win

ggplot(mpg, aes(x = displ, y = hwy, color = drv)) + 
  geom_point(color = "blue") 

# SETUP: We will need tidyverse and an example graphic

library(tidyverse)

p <- 
  ggplot(mpg, aes(x = displ, y = hwy, color = drv)) + 
  geom_point() +
  labs(title = "Fuel Efficiency")
p

# ==============================================================================

# USECASE: Apply a "complete" theme

p + theme_bw()

p + theme_classic()

p + theme_dark()

# ==============================================================================

# LESSON: More more precise control, we can use theme()

p + theme(legend.position = "top")

p + theme(plot.title = element_text(color = "purple", face = "bold"))

p + theme(panel.grid = element_blank())

# NOTE: There are a lot of elements to learn, so use a cheatsheet!

# SETUP: We will need tidyverse and an example graphic

library(tidyverse)

p <- ggplot(mpg, aes(x = displ, y = hwy)) + 
  geom_point() + geom_smooth() +
  labs(x = "Engine Displacement", y = "Highway MPG")
p

# ==============================================================================

# USECASE: Save a specific ggplot object to a file

ggsave(filename = "pfinal.png", plot = p)

# ==============================================================================

# LESSON: Specify the size of the file to create

ggsave(filename = "pfinal2.png", plot = p, 
       width = 6, height = 3, units = "in")

# ==============================================================================

# LESSON: Just change the extension to create a different file type

ggsave(filename = "pfinal2.pdf", plot = p, 
       width = 6, height = 3, units = "in")

# ==============================================================================

# PITFALL: Creating a very large file may lead to small text

ggsave(filename = "p_poster.png", plot = p, 
       width = 12, height = 8, units = "in")

# ==============================================================================

# TIP: You can quickly increase the text size using base_size

p2 <- p + theme_grey(base_size = 24)

ggsave(filename = "p_poster2.png", plot = p2,
       width = 12, height = 8, units = "in")